Acoustic Emission-Based Diagnosis Using AlexNet: How Wave Propagation Effects Classification Performance

Acoustic Emission-Based Diagnosis Using AlexNet: How Wave Propagation Effects Classification Performance

Sebastian Felix Wirtz, Sevki Onur Doruk, Dirk Söffker

download PDF

Abstract. Composite materials are frequently used due to light weight and high stiffness. However, the use of composite materials is limited due to several micro-mechanical damage mechanisms, which are currently not well understood. Therefore, Acoustic Emission (AE) is frequently suggested for in-situ diagnosis of composite materials in Structural Health Monitoring. Elastic stress waves in the ultrasound regime are recorded using highly sensitive measurement equipment. Based on suitable analysis and interpretation of the waveform data, different micro-mechanical damage mechanisms such as delamination or fiber breakage can be distinguished. Frequently, data-driven approaches are suggested for classification of AE data. In literature, attenuation of AE due to wave propagation is currently the main limiting factor in AE-based diagnosis. In particular, AE is strongly attenuated in composite materials due to dispersion as dominant attenuation mechanism. Furthermore, depending on the source location, which is usually not known a-priori, different propagation paths are obtained in practice. Therefore, the effect of wave propagation on AE is important and can not be neglected to achieve reliable classification. However, the effect of different propagation paths on the classification performance is often not considered explicitly. Due to dependence of wave propagation behavior on waveform characteristics (e.g. frequency), it can be expected that the impact of wave propagation on AE classification performance depends also on the related source mechanism. Therefore, it is worth to study how classification performance of different source mechanisms is effected by wave propagation. In this paper, the dependence of the classification performance on different propagation distances is experimentally investigated in detail. To achieve highly reproducible AE measurements, different artificial AE sources are induced using surface mounted piezo elements. The corresponding waveforms are measured at two different locations. For classification, a convolutional neural network-based classification scheme is established. The pre-trained AlexNet architecture is fine-tuned using measurements obtained using different excitation signals. The classification performance is evaluated with particular focus on the impact of wave propagation. The variations in propagation distance have a strong impact on the classification performance. As main conclusion for AE-based SHM it can be stated that variations in the propagation path should be considered. Furthermore, the underlying source mechanisms should be taken into consideration for reliable performance estimation.

Acoustic Emission, Convolutional Neural Network, Classification, Diagnosis, Reliability, Composite Materials

Published online 2/20/2021, 9 pages
Copyright © 2021 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA

Citation: Sebastian Felix Wirtz, Sevki Onur Doruk, Dirk Söffker, Acoustic Emission-Based Diagnosis Using AlexNet: How Wave Propagation Effects Classification Performance, Materials Research Proceedings, Vol. 18, pp 186-194, 2021


The article was published as article 22 of the book Structural Health Monitoring

Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.

[1] D. Baccar and D. Söffker, Identification and classification of failure modes in laminated composites by using a multivariate statistical analysis of wavelet coefficients. Mech Syst Signal Pr 96 (2017) 77-87.
[2] F. Dahmene, S. Yaacoubi, M. El Mountassir, N. Bendaoud, C. Langlois and O. Bardoux, On the modal acoustic emission testing of composite structure. Compos Struct, 140 (2016) 446-452.
[3] J. Martínez-Jequier, A. Gallego, E. Suárez, F. J. Juanes and Á. Valea, Real-time damage mechanisms assessment in CFRP samples via acoustic emission Lamb wave modal analysis. Compos Part B-Eng 68 (2015) 317-326.
[4] S. K. Chelliah, P. Parameswaran, S. Ramasamy, A. Vellayaraj and S. Subramanian, Optimization of acoustic emission parameters to discriminate failure modes in glass–epoxy composite laminates using pattern recognition. Struct Health Monit 18 (2019) 1253-1267.
[5] J. P. McCrory, S. K. Al-Jumaili, D. Crivelli, M. R. Pearson, M. J. Eaton, C. A. Featherston, M. Guagliano, K. M. Holford and R. Pullin, Damage classification in carbon fibre composites using acoustic emission: A comparison of three techniques. Compos Part B-Eng 68 (2015) 424-430.
[6] N. Beheshtizadeh and A. Mostafapour, Processing of acoustic signals via wavelet & Choi-Williams analysis in three-point bending load of carbon/epoxy and glass/epoxy composites. Ultrasonics 79 (2017) 1-8.
[7] S. K. Al-Jumaili, K. M. Holford, M. J. Eaton and R. Pullin, Parameter Correction Technique (PCT): A novel method for acoustic emission characterisation in large-scale composites. Compos Part B-Eng 75 (2015) 336-344.
[8] E. Maillet, C. Baker, G. N. Morscher, V. V. Pujar and J. R. Lemanski, Feasibility and limitations of damage identification in composite materials using acoustic emission. Compos Part A-Appl S 75 (2015) 77-83.
[9] K. Asamene, L. Hudson and M. Sundaresan, Influence of attenuation on acoustic emission signals in carbon fiber reinforced polymer panels. Ultrasonics 59 (2015) 86-93.
[10] M. Kharrat, V. Placet, E. Ramasso and M. L. Boubakar, Influence of damage accumulation under fatigue loading on the AE-based health assessment of composite materials: Wave distortion and AE-features evolution as a function of damage level. Compos Part A-Appl S 109 (2018) 615-627.
[11] S. F. Wirtz, S. Bach and D. Söffker, Experimental results of acoustic emission attenuation due to wave propagation in composites. Annual Conference of the PHM Society, Scottsdale, AZ, USA, September 21-26, 2019.
[12] Z. Su and L. Ye, Selective generation of Lamb wave modes and their propagation charac-teristics in defective composite laminates. P I Mech Eng L-J Mat 218 (2004) 95-110.
[13] M. Azimi, A. D. Eslamlou and G. Pekcan, Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review. Sensors 20 (2020) 2778.
[14] A. Krizhevsky, I. Sutskever and G. E. Hinton, ImageNet Classification with Deep Convo-lutional Neural Networks. Adv Neur In 25 (2012) 1097-1105.
[15] S. Dorafshan, R. J. Thomas and M. Maguire, Comparison of deep convolutional neural net-works and edge detectors for image-based crack detection in concrete, Constr Build Mater 186 (2018) 1031-1045.
[16] M. Hemmer, H. Van Khang, K. Robbersmyr, T. Waag and T. Meyer, Fault Classification of Axial and Radial Roller Bearings Using Transfer Learning through a Pretrained Convolutional Neural Network. Designs 2 (2018) 56.
[17] S. Lu, Z. Lu and Y. D. Zhang, Pathological brain detection based on AlexNet and transfer learning. J Comput Sci-Neth 30 (2019) 41-47.